This paper suggests a method to generalise principal component analysis by transforming in adaptive way both original variables and their principal components by non-linear functions, i.e., B-splines. The main advantage is improving the model fit, taking into account non-linear relationships and displaying data in a clearer way via principal surfaces.
Adaptive Non-linear Principal Component and Surface Analysis
LOMBARDO, Rosaria;
2009
Abstract
This paper suggests a method to generalise principal component analysis by transforming in adaptive way both original variables and their principal components by non-linear functions, i.e., B-splines. The main advantage is improving the model fit, taking into account non-linear relationships and displaying data in a clearer way via principal surfaces.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
